Topic
Cloudflare
14 episodes
-
MCP Goes Stateless, and Developers Ask Whether That Just Makes It an API Again
MCP's July 28, 2026 release strips away protocol sessions and stateful handshakes, moving to a fully stateless architecture with metadata pushed into HTTP headers. The shift solves real scaling problems—load balancing, autoscaling, session migration—but it also reveals what MCP actually is: a REST API with a JSON-RPC convention on top and an auth layer below. The community is split not on whether statelessness is better, but on whether the protocol needed to exist at all once you've peeled back to REST plus headers.
-
Model Behavior: Week of August 10, 2026
We argue this week is about who owns the AI control plane, not who tops a leaderboard, and we use Cloudflare, LangSmith, Moshi, Anthropic, and the new open-model policy split as our evidence. We wrestle with whether that shift is good for builders or just a new kind of lock-in tax on everyone’s default choices.
-
Unifying Workers AI and AI Gateway into a single AI control plane
Pippa and Tyler dig into Cloudflare’s move to unify Workers AI and AI Gateway into one AI control plane, arguing over whether it’s a real simplification for developers or mostly a packaging move around the same underlying routing and billing layer. They land on it being genuinely useful if you already live in Cloudflare’s ecosystem, but not magically solving the hard parts of model choice, observability, or provider lock-in.
-
Model Behavior: Week of August 3, 2026
We spent this week arguing that the frontier race has quietly turned into a battle for the default, not the smartest model, and we used the price war and agent stacks as our receipts. We’re both a little uneasy about how much power is moving into routing layers and “lifecycle” platforms while everyone pretends it’s just about cheaper tokens.
-
The Agent Development Lifecycle has arrived on Cloudflare
Jessica and Cathy dig into Cloudflare packaging the messy agent workflow into something that looks a lot more like a real software lifecycle: building, tracing, testing, deploying, and maintaining agents on Workers with observability and workflow plumbing that already exists.
-
Your agent needs a computer, not a container — introducing @cloudflare/computer
Auden and Wren dig into Cloudflare’s early preview of @cloudflare/computer, a new agent runtime that gives each agent its own computer rather than a bare container. They focus on the user story, what’s actually new, and where the abstraction looks genuinely useful versus a little hand-wavy.
-
MCP server portals
Asteria and Draco unpack Cloudflare's MCP server portals as boundary infrastructure for enterprise MCP adoption: one Access-controlled endpoint, curated tools, managed OAuth, Code Mode, and observability, with caveats around direct server URLs, admin credentials, and sync paths.
-
Introducing Precursor: detecting agentic behavior with continuous client Side signals
Fern and Lintel dig into Cloudflare’s Precursor, a session-level bot detection layer that watches behavior across the whole journey instead of only at challenge points. They focus on the real argument: modern automation can fake isolated moments, but it’s much harder to fake a consistent human rhythm over time.
-
Your Worker can now have its own cache in front of it
Cloudflare launched Workers Cache, a tiered cache that sits in front of Worker code itself — not between the origin and Cloudflare. Single-line Wrangler config plus standard Cache-Control headers. On hit, Worker doesn't run (zero CPU cost); on miss, Worker runs and populates cache for the next request anywhere on Earth. The shift: Workers went from 'bolt-on transformation layer in front of origin' (2017) to 'the origin itself' (modern frameworks: Astro, Next.js, Remix, SvelteKit). Cache-in-front solves the SSR problem — server-render on demand, cache the response, refresh on TTL without build-time prerender cost. Stale-while-revalidate makes it feel instant (serve stale immediately, refresh in background). Full Vary support for content negotiation (same URL, multiple representations: WebP vs JPEG, English vs French, HTML vs JSON). Per-entrypoint cache control lets you compose caching into app structure. Available today to all Workers on any plan.
-
AI agents get their own phone directory built atop DNS
Cody and Justy dig into DNS-AID, a new Linux Foundation project that lets AI agents discover each other using DNS records instead of hardcoded configs. Cody's skeptical the world needed another spec layer; Justy thinks the infrastructure bet is actually smart. They work through what it does, what it doesn't solve, and whether the McKinsey trillion-dollar number means anything at all.
-
Cloudflare Completes Its Agent Infrastructure Stack with Browser Run Rebuild and Six Layer Platform
Justy and Cody dig into Cloudflare's rebuilt Browser Run and the six-layer agent infrastructure stack it anchors. They debate whether the "most complete agent platform outside the hyperscalers" claim holds up, unpack the D1/Queues migration and 500k container capacity numbers, and argue about what "most complete" actually means for developers choosing a platform.
-
Cloudflare Launches Code Mode MCP Server to Optimize Token Usage for AI Agents
Cloudflare's new Model Context Protocol (MCP) server powered by Code Mode reduces token usage for AI agents, making it possible to interact with complex APIs more efficiently.
-
Cloudflare’s new Dynamic Workers ditch containers to run AI agent code 100x faster
Cloudflare launches Dynamic Workers, ditching containers for millisecond-starting isolates that run AI agent code 100x faster. The tech enables 'Code Mode' — where LLMs write TypeScript functions instead of chaining tool calls, cutting token usage by 81%. Built on V8 isolates, it's positioning sandboxing as a strategic layer in the AI stack.
-
Introducing Moltworker: a self hosted personal AI agent, minus the minis
In this episode, we explore Moltworker, a self-hosted personal AI agent that operates seamlessly on Cloudflare's infrastructure. We discuss its implications for privacy, the power of self-hosting, and how it simplifies AI integration for everyday users.